Project

clag

0.0
The project is in a healthy, maintained state
Clag is a command line tool that generates command line commands right in your terminal and puts it into your clipboard for you to paste into your terminal.
2005
2006
2007
2008
2009
2010
2011
2012
2013
2014
2015
2016
2017
2018
2019
2020
2021
2022
2023
2024
 Dependencies

Development

~> 10.0

Runtime

 Project Readme

clag - Command Line AI Gem

Tired of trying to remember the exact flags to use or digging through documentation or googling to find how to do the thing you're trying to do?

Suffer no more! Simply describe what you're trying to do and generate the command with the help of an LLM!

Installation

  • Install the gem gem install clag

  • Generate commands clag g "create a new ruby on rails project using postgres and tailwindcss"

Using OpenAI's GPT-4

Using Google's Gemini 1.0

  • Get an API key from Google's AI Studio at https://ai.google.dev/

  • Set your API key as GEMINI_API_KEY in your environment

  • Select Gemini as your preferred LLM by setting CLAG_LLM=gemini in your environment

Using Anthropic's Claude 3 Opus

  • Get an API key from Anthropic at https://www.anthropic.com/

  • Set your API key as ANTHROPIC_API_KEY in your environment

  • Select Claude 3 Opus as your preferred LLM by setting CLAG_LLM=claude in your environment

Using Groq on Mixtral

  • Get an API key from https://console.groq.com/

  • Set your API key as GROQ_API_KEY in your environment

  • Select Groq as your preferred LLM by setting CLAG_LLM=groq in your environment

Using a Local Model

  • Have a model locally from either Ollama or Llamafile with an OpenAI compatible API

  • Have the API server running on port 8080

  • Select local as your preferred LLM by setting CLAG_LLM=local in your environment

Usage

Currently support one command: "g".

clag g "the command you'd like to generate"

Contributing

Bug reports and pull requests are welcome on Github at https://github.com/sublayerapp/clag

Community

Like what you see, or looking for more people working on the future of programming with LLMs? Come join us in the Promptable Architecture Discord